© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38222
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enormes
    -1.02
    Objetivo
    -0.97
    curator
    -0.96
    bular
    -0.92
     AppBundle
    -0.90
     connaît
    -0.89
     TMPro
    -0.87
    nemies
    -0.86
    rester
    -0.85
    olalar
    -0.85
    POSITIVE LOGITS
     but
    0.86
     キャン
    0.76
    ধ
    0.75
     endometrial
    0.72
     aforementioned
    0.72
    大部分
    0.71
    意的
    0.71
    Auth
    0.70
     termites
    0.69
     thermometers
    0.69
    Activations Density 0.019%

    No Known Activations